paper-with-me

홈 › Papers

LEANN: A Low-Storage Vector Index

2025-06-09 · Yichuan Wang, Shu Liu, Zhifei Li, Yongji Wu, Ziming Mao, Yilong Zhao, Xiao Yan, Zhiying Xu, Yang Zhou, Ion Stoica, Sewon Min, Matei Zaharia, Joseph E. Gonzalez

Embedding-based search is widely used in applications such as recommendation and retrieval-augmented generation (RAG). Recently, there is a growing demand to support these capabilities over personal data stored locally on devices. However, maintaining the necessary data structure associated with the embedding-based search is often infeasible due to its high storage overhead. For example, indexing 100 GB of raw data requires 150 to 700 GB of storage, making local deployment impractical. Reducing this overhead while maintaining search quality and latency becomes a critical challenge. In this paper, we present LEANN, a storage-efficient approximate nearest neighbor (ANN) search index optimized for resource-constrained personal devices. LEANN combines a compact graph-based structure with an efficient on-the-fly recomputation strategy to enable fast and accurate retrieval with minimal storage overhead. Our evaluation shows that LEANN reduces index size to under 5% of the original raw data, achieving up to 50 times smaller storage than standard indexes, while maintaining 90% top-3 recall in under 2 seconds on real-world question answering benchmarks.

📄 PDF Abstract BibTeX arXiv:2506.08276

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringRAGRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Characterizing the Dilemma of Performance and Index Size in Billion-Scale Vector Search and Breaking It with Second-Tier Memory

2024-05-06 · Rongxin Cheng, Yifan Peng, Xingda Wei, Hongrui Xie 외

Vector searches on large-scale datasets are critical to modern online services like web search and RAG, which necessity storing the datasets and their index on the secondary storage like SSD. In this paper, we are the fi…

RAG

MINT: Multi-Vector Search Index Tuning

2025-04-28 · Jiongli Zhu, Yue Wang, Bailu Ding, Philip A. Bernstein 외

Vector search plays a crucial role in many real-world applications. In addition to single-vector search, multi-vector search becomes important for multi-modal and multi-feature scenarios today. In a multi-vector database…

CLEANN: Accelerated Trojan Shield for Embedded Neural Networks

2020-09-04 · Mojan Javaheripi, Mohammad Samragh, Gregory Fields, Tara Javidi 외

We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications. A Trojan attack works by injecting a backdoor in the DNN while training; du…

Dictionary Learning

Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search

2025-01-16 · Daniel Severo, Giuseppe Ottaviano, Matthew Muckley, Karen Ullrich 외

Approximate nearest neighbor search for vectors relies on indexes that are most often accessed from RAM. Therefore, storage is the factor limiting the size of the database that can be served from a machine. Lossy vector …

Quantization

HoneyBee: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning

2025-05-02 · Hongbin Zhong, Matthew Lentz, Nina Narodytska, Adriana Szekeres 외

As vector databases gain traction in enterprise applications, robust access control has become critical to safeguard sensitive data. Access control in these systems is often implemented through hybrid vector queries, whi…